© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9814
    Prev
    Next
    INDEX
    Explanations

    references to image processing and manipulation in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding "image"

    np_acts-logits-general · gemini-2.0-flash

    image context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.63
    OGND
    -0.62
    RegressionTest
    -0.61
     setuptools
    -0.58
    argout
    -0.57
    rawtypes
    -0.56
    RectangleBorder
    -0.56
    apunov
    -0.56
    Portale
    -0.53
    MLLoader
    -0.50
    POSITIVE LOGITS
     image
    4.00
    image
    3.56
     Image
    3.47
     images
    3.33
    Image
    3.26
     IMAGE
    3.08
     Images
    2.91
    IMAGE
    2.86
     imagem
    2.72
     imagen
    2.71
    Activations Density 0.382%

    No Known Activations